© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 175190
    Prev
    Next
    INDEX
    Explanations

    miles from

    np_acts-logits-general · gemini-2.5-flash-lite

    handle, higher, owner, same, Atlas, yarns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phang
    0.54
     Plow
    0.52
    in
    0.51
    es
    0.50
    pl
    0.49
     Pache
    0.49
     ጠ
    0.49
     Mahmud
    0.48
    ot
    0.48
    pline
    0.48
    POSITIVE LOGITS
    第六
    0.52
    訕
    0.50
    ワード
    0.48
    是
    0.46
    一大
    0.46
    周期
    0.46
    一名
    0.45
    兩
    0.45
    一组
    0.44
    世界上最大的
    0.44
    Activations Density 0.000%

    No Known Activations